Accuracy of Segmentation of a Commercial Computer-aided Detection System for Mammography
Authors:
- Jay A. BakerJBJay A. Baker
- Eric L. RosenEREric L. Rosen
- Michele M. CrockettMCMichele M. Crockett
- Joseph Y. LoJLJoseph Y. Lo
- 1 May 2005
- journal article
- research article
- Published by Radiological Society of North America (RSNA) in Radiology
- Vol. 235 (2) , 385-390
Abstract
To assess the accuracy of segmentation in a commercially available computer-aided detection (CAD) system. Approval for this study was obtained from the authors' institutional review board. Informed consent was not required by the board for this review, as data were stripped of patient identifiers. Two thousand twenty mammograms from 507 women were analyzed with the hardware and software of a commercial CAD system. The accuracy of the segmentation process was determined semiquantitatively and categorized as near perfect if the skin line of the breast was accurately detected, acceptable if only subcutaneous fat was excluded, or unacceptable if any breast parenchyma was excluded from consideration. The accuracy of segmentation was compared for different breast densities and film sizes by using logistic regression (P < .05). Overall, segmentation was near perfect or acceptable in almost 96.8% of images. However, segmentation defects were significantly more common in mammograms with heterogeneously dense breast tissue (8% unacceptable) than in those with fatty replaced (0% unacceptable), scattered (1.2% unacceptable), or extremely dense (1.8% unacceptable) breast parenchyma (P < .05). For images with unacceptable segmentation, the average percentage of breast parenchyma excluded was almost 25% (range, 5%-100%), with no significant differences among breast densities. For one commercial CAD system, segmentation was usually near perfect or acceptable but was unacceptable more than five times more frequently for mammograms of breasts with heterogeneously dense parenchyma than for those with all other breast densities. On average, one-quarter of the breast parenchyma was excluded from CAD analysis for images with unacceptable segmentation.Keywords
This publication has 18 references indexed in Scilit:
- Improvement in Sensitivity of Screening Mammography with Computer-Aided Detection:A Multiinstitutional TrialAmerican Journal of Roentgenology, 2003
- Automated detection of lung nodules in CT scans: Effect of image reconstruction algorithmMedical Physics, 2003
- Computer-aided preoperative diagnosis of microcalcifications on mammogramsActa Radiologica, 2003
- Breast Cancer: Effectiveness of Computer-aided Diagnosis—Observer Study with Independent Database of MammogramsRadiology, 2002
- Screening Mammography with Computer-aided Detection: Prospective Study of 12,860 Patients in a Community Breast CenterRadiology, 2001
- Potential Contribution of Computer-aided Detection to the Sensitivity of Screening MammographyRadiology, 2000
- Improvement of Radiologists' Characterization of Mammographic Masses by Using Computer-aided Diagnosis: An ROC StudyRadiology, 1999
- The Use of an Interactive Software Program for Quantitative Characterization of Microcalcifications on Digitized Film-Screen MammogramsInvestigative Radiology, 1999
- Automatic detection of breast border and nipple in digital mammogramsComputer Methods and Programs in Biomedicine, 1996
- Automated segmentation of digitized mammogramsAcademic Radiology, 1995